【信号处理】基于DGGAN的单通道脑电信号增强和情绪检测（tensorflow）

关于

情绪检测，是脑科学研究中的一个常见和热门的方向。在进行情绪检测的分类中，真实数据不足，经常导致情绪检测模型的性能不佳。因此，对数据进行增强，成为了一个提升下游任务的重要的手段。本项目通过DCGAN模型实现脑电信号的扩充。

图片来源：https://www.medicalnewstoday.com/articles/seizure-eeg

工具

数据

方法实现

DCGAN速递：https://arxiv.org/abs/1511.06434

数据加载和预处理

python 复制代码

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from sklearn.preprocessing import StandardScaler
from tensorflow.keras.utils import to_categorical
from sklearn.model_selection import train_test_split
import tensorflow as tf
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.layers import Embedding
from tensorflow.keras.layers import LSTM
from tensorflow.keras.optimizers import SGD
from sklearn.metrics import accuracy_score
from model_DCGAN import DCGAN
from tensorflow.keras.optimizers import Adam, SGD, RMSprop
from sklearn.utils import shuffle
from sklearn.ensemble import GradientBoostingClassifier

use_feature_reduction = True

tf.keras.backend.clear_session()

df=pd.read_csv('dataset/emotions.csv')

encode = ({'NEUTRAL': 0, 'POSITIVE': 1, 'NEGATIVE': 2} )
#new dataset with replaced values
df_encoded = df.replace(encode)

print(df_encoded.head())
print(df_encoded['label'].value_counts()),

x=df_encoded.drop(["label"]  ,axis=1)
y = df_encoded.loc[:,'label'].values

scaler = StandardScaler()
scaler.fit(x)
x = scaler.transform(x)
y = to_categorical(y)

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 4)

if use_feature_reduction:
    # Feature reduction part
    est = GradientBoostingClassifier(n_estimators=10, learning_rate=0.1, random_state=0).fit(x_train,
                                                                                             y_train.argmax(-1))

    # Obtain feature importance results from Gradient Boosting Regressor
    feature_importance = est.feature_importances_
    epsilon_feature = 1e-2
    x_train = x_train[:, feature_importance > epsilon_feature]
    x_test = x_test[:, feature_importance > epsilon_feature]

设置DCGAN优化器

python 复制代码

# setup optimzers
gen_optim = Adam(1e-4, beta_1=0.5)
disc_optim = RMSprop(5e-4)

训练GAN生成类别0脑电数据

python 复制代码

# generate samples for class 0
generator_class = 0
dcgan = DCGAN(gen_optim, disc_optim, noise_dim=100, dropout=0.3, input_dim=x_train.shape[2])
x_train_class_0 = x_train[y_train[:,generator_class]==1,:]
loss_history_class_0, acc_history_class_0, grads_history_class_0 = dcgan.train(x_train_class_0, epochs=100)
print("Class 0 fake samples are generating")
generator_class_0 = dcgan.generator
generated_samples_class_0, _ = dcgan.generate_fake_data(N=len(x_train_class_0))

训练GAN生成类别1脑电数据

python 复制代码

# generate samples for class 1
generator_class = 1
dcgan = DCGAN(gen_optim, disc_optim, noise_dim=100, dropout=0.3, input_dim=x_train.shape[2])
x_train_class_1 = x_train[y_train[:,generator_class]==1,:]
loss_history_class_1, acc_history_class_1, grads_history_class_1 = dcgan.train(x_train_class_1, epochs=100)
print("Class 1 fake samples are generating")
generator_class_1 = dcgan.generator
generated_samples_class_1, _ = dcgan.generate_fake_data(N=len(x_train_class_1))

训练GAN生成类别2脑电数据

python 复制代码

# generate samples for class 2
generator_class = 2
dcgan = DCGAN(gen_optim, disc_optim, noise_dim=100, dropout=0.3, input_dim=x_train.shape[2])
x_train_class_2 = x_train[y_train[:,generator_class]==1,:]
loss_history_class_2, acc_history_class_2, grads_history_class_2 = dcgan.train(x_train_class_2,epochs=100)
print("Class 2 fake samples are generating")
generator_class_2 = dcgan.generator
generated_samples_class_2, _ = dcgan.generate_fake_data(N=len(x_train_class_2))

合成数据融入真实训练数据集

python 复制代码

generated_samples = np.concatenate((generated_samples_class_0,
                                    generated_samples_class_1,
                                    generated_samples_class_2),axis=0)
generated_y =np.concatenate((np.zeros((len(x_train_class_0),),dtype=np.int32),
                             np.ones((len(x_train_class_1),),dtype=np.int32),
                             2 * np.ones((len(x_train_class_2),),dtype=np.int32)),axis=0)

generated_y = to_categorical(generated_y)

x_train_all = np.concatenate((x_train,generated_samples),axis=0)
y_train_all = np.concatenate((y_train,generated_y), axis=0)


#shuffle training data
x_train_all, y_train_all = shuffle(x_train_all,y_train_all)

基于数据增强的LSTM模型情绪检测

python 复制代码

model = Sequential()
model.add(LSTM(64, input_shape=(1,x_train_all.shape[2]),activation="relu",return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(32,activation="sigmoid"))
model.add(Dropout(0.2))
model.add(Dense(3, activation='sigmoid'))
model.compile(loss = 'categorical_crossentropy', optimizer = "adam", metrics = ['accuracy'])
model.summary()


history = model.fit(x_train_all, y_train_all, epochs = 250, validation_data= (x_test, y_test))
score, acc = model.evaluate(x_test, y_test)

pred = model.predict(x_test)
predict_classes = np.argmax(pred,axis=1)
expected_classes = np.argmax(y_test,axis=1)
print(expected_classes.shape)
print(predict_classes.shape)
correct = accuracy_score(expected_classes,predict_classes)
print(f"Test Accuracy: {correct}")

已附DCGAN模型

相关项目和代码问题，欢迎沟通交流。